Reinforcement Learning Engineer

About the Role

Auron Solutions builds Physical AI and software-defined EW platforms for real-time signal intelligence. As Reinforcement Learning Engineer, you will build the autonomous decision engine that acts on live signal data — designing and training RL policies, modelling the operational environment in simulation, and owning the full sim-to-real transition for deployed edge systems.

Key Responsibilities

• 1

  Design, implement, and train reinforcement learning policies for autonomous decision-making on real-time signal intelligence.

• 2

  Model the operational environment in simulation to generate training data and evaluate policy robustness.

• 3

  Own the sim-to-real transition: bridge the gap between simulated training and live hardware deployment.

• 4

  Integrate RL decision outputs with the ML signal classification pipeline and FPGA hardware layer.

• 5

  Continuously evaluate and improve policy performance using real-world signal feedback and operational data.

Requirements

• Strong proficiency in Python and RL frameworks: OpenAI Gym, Stable Baselines, RLlib, or similar.
• Experience designing reward functions, environment models, and training pipelines for RL agents.
• Familiarity with sim-to-real transfer techniques and challenges in physical deployment.
• Ability to work independently with high ownership in an early-stage startup environment.
• Bonus: experience with RF environments, electronic warfare, or signal intelligence applications.

Skills Required

How The Selection Process Works

Make Your Resume ATS-Friendly

Important Application Guidelines